Towards robust identification and tracking of nevi in sparse photographic time series

Jakob Vogel, Alexandru Duliu, Yuji Oyamada, Jose Gardiazabal, Tobias Lasser, Mahzad Ziai, Rüdiger Hein, Nassir Navab

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In dermatology, photographic imagery is acquired in large volumes in order to monitor the progress of diseases, especially melanocytic skin cancers. For this purpose, overview (macro) images are taken of the region of interest and used as a reference map to re-localize highly magni ed images of individual lesions. The latter are then used for diagnosis. These pictures are acquired at irregular intervals under only partially constrained circumstances, where patient positions as well as camera positions are not reliable. In the presence of a large number of nevi, correct identi cation of the same nevus in a series of such images is thus a time consuming task with ample chances for error. This paper introduces a method for largely automatic and simultaneous identi cation of nevi in di erent images, thus allowing the tracking of a single nevus over time, as well as pattern evaluation. The method uses a rotation-invariant feature descriptor that uses the local neighborhood of a nevus to describe it. The texture, size and shape of the nevus are not used to describe it, as these can change over time, especially in the case of a malignancy. We then use the Random Walks framework to compute the correspondences based on the probabilities derived from comparing the feature vectors. Evaluation is performed on synthetic and patient data at the university clinic.

    Original languageEnglish
    Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
    PublisherSPIE
    Volume9035
    ISBN (Print)9780819498281
    DOIs
    Publication statusPublished - 2014
    EventMedical Imaging 2014: Computer-Aided Diagnosis - San Diego, CA
    Duration: 2014 Feb 182014 Feb 20

    Other

    OtherMedical Imaging 2014: Computer-Aided Diagnosis
    CitySan Diego, CA
    Period14/2/1814/2/20

    Fingerprint

    Nevus
    Cations
    Time series
    Positive ions
    Dermatology
    Macros
    Skin
    Textures
    Cameras
    dermatology
    cations
    evaluation
    random walk
    imagery
    lesions
    textures
    cancer
    Imagery (Psychotherapy)
    cameras
    Skin Neoplasms

    Keywords

    • Biomedical Imaging
    • Dermatology
    • Feature Descriptor
    • Random Walks
    • Robust Matching

    ASJC Scopus subject areas

    • Atomic and Molecular Physics, and Optics
    • Electronic, Optical and Magnetic Materials
    • Biomaterials
    • Radiology Nuclear Medicine and imaging

    Cite this

    Vogel, J., Duliu, A., Oyamada, Y., Gardiazabal, J., Lasser, T., Ziai, M., ... Navab, N. (2014). Towards robust identification and tracking of nevi in sparse photographic time series. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 9035). [90353D] SPIE. https://doi.org/10.1117/12.2043788

    Towards robust identification and tracking of nevi in sparse photographic time series. / Vogel, Jakob; Duliu, Alexandru; Oyamada, Yuji; Gardiazabal, Jose; Lasser, Tobias; Ziai, Mahzad; Hein, Rüdiger; Navab, Nassir.

    Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014. 90353D.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Vogel, J, Duliu, A, Oyamada, Y, Gardiazabal, J, Lasser, T, Ziai, M, Hein, R & Navab, N 2014, Towards robust identification and tracking of nevi in sparse photographic time series. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9035, 90353D, SPIE, Medical Imaging 2014: Computer-Aided Diagnosis, San Diego, CA, 14/2/18. https://doi.org/10.1117/12.2043788
    Vogel J, Duliu A, Oyamada Y, Gardiazabal J, Lasser T, Ziai M et al. Towards robust identification and tracking of nevi in sparse photographic time series. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035. SPIE. 2014. 90353D https://doi.org/10.1117/12.2043788
    Vogel, Jakob ; Duliu, Alexandru ; Oyamada, Yuji ; Gardiazabal, Jose ; Lasser, Tobias ; Ziai, Mahzad ; Hein, Rüdiger ; Navab, Nassir. / Towards robust identification and tracking of nevi in sparse photographic time series. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9035 SPIE, 2014.
    @inproceedings{409ef5d209b54bae8389b7b00ad41ef6,
    title = "Towards robust identification and tracking of nevi in sparse photographic time series",
    abstract = "In dermatology, photographic imagery is acquired in large volumes in order to monitor the progress of diseases, especially melanocytic skin cancers. For this purpose, overview (macro) images are taken of the region of interest and used as a reference map to re-localize highly magni ed images of individual lesions. The latter are then used for diagnosis. These pictures are acquired at irregular intervals under only partially constrained circumstances, where patient positions as well as camera positions are not reliable. In the presence of a large number of nevi, correct identi cation of the same nevus in a series of such images is thus a time consuming task with ample chances for error. This paper introduces a method for largely automatic and simultaneous identi cation of nevi in di erent images, thus allowing the tracking of a single nevus over time, as well as pattern evaluation. The method uses a rotation-invariant feature descriptor that uses the local neighborhood of a nevus to describe it. The texture, size and shape of the nevus are not used to describe it, as these can change over time, especially in the case of a malignancy. We then use the Random Walks framework to compute the correspondences based on the probabilities derived from comparing the feature vectors. Evaluation is performed on synthetic and patient data at the university clinic.",
    keywords = "Biomedical Imaging, Dermatology, Feature Descriptor, Random Walks, Robust Matching",
    author = "Jakob Vogel and Alexandru Duliu and Yuji Oyamada and Jose Gardiazabal and Tobias Lasser and Mahzad Ziai and R{\"u}diger Hein and Nassir Navab",
    year = "2014",
    doi = "10.1117/12.2043788",
    language = "English",
    isbn = "9780819498281",
    volume = "9035",
    booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
    publisher = "SPIE",

    }

    TY - GEN

    T1 - Towards robust identification and tracking of nevi in sparse photographic time series

    AU - Vogel, Jakob

    AU - Duliu, Alexandru

    AU - Oyamada, Yuji

    AU - Gardiazabal, Jose

    AU - Lasser, Tobias

    AU - Ziai, Mahzad

    AU - Hein, Rüdiger

    AU - Navab, Nassir

    PY - 2014

    Y1 - 2014

    N2 - In dermatology, photographic imagery is acquired in large volumes in order to monitor the progress of diseases, especially melanocytic skin cancers. For this purpose, overview (macro) images are taken of the region of interest and used as a reference map to re-localize highly magni ed images of individual lesions. The latter are then used for diagnosis. These pictures are acquired at irregular intervals under only partially constrained circumstances, where patient positions as well as camera positions are not reliable. In the presence of a large number of nevi, correct identi cation of the same nevus in a series of such images is thus a time consuming task with ample chances for error. This paper introduces a method for largely automatic and simultaneous identi cation of nevi in di erent images, thus allowing the tracking of a single nevus over time, as well as pattern evaluation. The method uses a rotation-invariant feature descriptor that uses the local neighborhood of a nevus to describe it. The texture, size and shape of the nevus are not used to describe it, as these can change over time, especially in the case of a malignancy. We then use the Random Walks framework to compute the correspondences based on the probabilities derived from comparing the feature vectors. Evaluation is performed on synthetic and patient data at the university clinic.

    AB - In dermatology, photographic imagery is acquired in large volumes in order to monitor the progress of diseases, especially melanocytic skin cancers. For this purpose, overview (macro) images are taken of the region of interest and used as a reference map to re-localize highly magni ed images of individual lesions. The latter are then used for diagnosis. These pictures are acquired at irregular intervals under only partially constrained circumstances, where patient positions as well as camera positions are not reliable. In the presence of a large number of nevi, correct identi cation of the same nevus in a series of such images is thus a time consuming task with ample chances for error. This paper introduces a method for largely automatic and simultaneous identi cation of nevi in di erent images, thus allowing the tracking of a single nevus over time, as well as pattern evaluation. The method uses a rotation-invariant feature descriptor that uses the local neighborhood of a nevus to describe it. The texture, size and shape of the nevus are not used to describe it, as these can change over time, especially in the case of a malignancy. We then use the Random Walks framework to compute the correspondences based on the probabilities derived from comparing the feature vectors. Evaluation is performed on synthetic and patient data at the university clinic.

    KW - Biomedical Imaging

    KW - Dermatology

    KW - Feature Descriptor

    KW - Random Walks

    KW - Robust Matching

    UR - http://www.scopus.com/inward/record.url?scp=84902096197&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84902096197&partnerID=8YFLogxK

    U2 - 10.1117/12.2043788

    DO - 10.1117/12.2043788

    M3 - Conference contribution

    SN - 9780819498281

    VL - 9035

    BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

    PB - SPIE

    ER -